[PATCH 1/4] perf tools: add Java demangling support

[Stephane Eranian <eranian@google.com>]

Add Java function descriptor demangling support.
Something bfd cannot do.

Signed-off-by: Stephane Eranian <eranian@google.com>
---
 tools/perf/util/symbol-elf.c |   2 +
 tools/perf/util/symbol.c     | 195 ++++++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/symbol.h     |   1 +
 3 files changed, 197 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index b24f9d8..71ee49b 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1019,6 +1019,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				demangle_flags = DMGL_PARAMS | DMGL_ANSI;
 
 			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
+			if (demangled == NULL)
+				demangled = java_demangle_sym(elf_name);
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index a690668..ef50343 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -9,6 +9,7 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <inttypes.h>
+#include <bfd.h>
 #include "build-id.h"
 #include "util.h"
 #include "debug.h"
@@ -1241,6 +1242,195 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 		return dso__split_kallsyms(dso, map, delta, filter);
 }
 
+enum {
+	MODE_PREFIX=0,
+	MODE_CLASS=1,
+	MODE_FUNC=2,
+	MODE_TYPE=3,
+	MODE_CTYPE=3, /* class arg */
+};
+
+#define BASE_ENT(c, n)	[c-'A']=n
+static const char *base_types['Z'-'A' + 1]={
+	BASE_ENT('B', "byte" ),
+	BASE_ENT('C', "char" ),
+	BASE_ENT('D', "double" ),
+	BASE_ENT('F', "float" ),
+	BASE_ENT('I', "int" ),
+	BASE_ENT('J', "long" ),
+	BASE_ENT('S', "short" ),
+	BASE_ENT('Z', "bool" ),
+};
+
+/*
+ * demangle Java symbol between str and end positions and stores
+ * up to maxlen characters into buf. The parser starts in mode.
+ *
+ * Use MODE_PREFIX to process entire prototype till end position
+ * Use MODE_TYPE to process return type if str starts on return type char
+ *
+ *  Return:
+ *	success: buf
+ *	error  : NULL
+ */
+static char *
+__demangle_java_sym(const char *str, const char *end, char *buf, int maxlen, int mode)
+{
+	int rlen = 0;
+	int array = 0;
+	int narg = 0;
+	const char *q;
+
+	if (!end)
+		end = str + strlen(str);
+
+	for (q = str; q != end; q++) {
+
+		if (rlen == (maxlen - 1))
+			break;
+
+		switch (*q) {
+		case 'L':
+			if (mode == MODE_PREFIX || mode == MODE_CTYPE) {
+				if (mode == MODE_CTYPE) {
+					if (narg)
+						rlen += snprintf(buf+rlen, maxlen - rlen, ", ");
+					narg++;
+				}
+				rlen += snprintf(buf+rlen, maxlen - rlen, "class ");
+				if (mode == MODE_PREFIX)
+					mode = MODE_CLASS;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case 'B':
+		case 'C':
+		case 'D':
+		case 'F':
+		case 'I':
+		case 'J':
+		case 'S':
+		case 'Z':
+			if (mode == MODE_TYPE) {
+				if (narg)
+					rlen += snprintf(buf+rlen, maxlen - rlen, ", ");
+				rlen += snprintf(buf+rlen, maxlen - rlen, "%s", base_types[*q - 'A']);
+				while(array--)
+					rlen += snprintf(buf+rlen, maxlen - rlen, "[]");
+				array = 0;
+				narg++;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case 'V':
+			if (mode == MODE_TYPE) {
+				rlen += snprintf(buf+rlen, maxlen - rlen, "void");
+				while(array--)
+					rlen += snprintf(buf+rlen, maxlen - rlen, "[]");
+				array = 0;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case '[':
+			if (mode != MODE_TYPE)
+				goto error;
+			array++;
+			break;
+		case '(':
+			if (mode != MODE_FUNC)
+				goto error;
+			buf[rlen++] = *q;
+			mode = MODE_TYPE;
+			break;
+		case ')':
+			if (mode != MODE_TYPE)
+				goto error;
+			buf[rlen++] = *q;
+			narg = 0;
+			break;
+		case ';':
+			if (mode != MODE_CLASS && mode != MODE_CTYPE)
+				goto error;
+			/* safe because at least one other char to process */
+			if (isalpha(*(q+1)))
+				rlen += snprintf(buf+rlen, maxlen - rlen, ".");
+			if (mode == MODE_CLASS)
+				mode = MODE_FUNC;
+			else if (mode == MODE_CTYPE)
+				mode = MODE_TYPE;
+			break;
+		case '/':
+			if (mode != MODE_CLASS && mode != MODE_CTYPE)
+				goto error;
+			rlen += snprintf(buf+rlen, maxlen - rlen, ".");
+			break;
+		default :
+			buf[rlen++] = *q;
+		}
+	}
+	buf[rlen] = '\0';
+	return buf;
+error:
+	return NULL;
+}
+
+/*
+ * Demangle Java function signature (Hotspot, not GCJ)
+ * input:
+ * 	str: string to parse. String is not modified
+ * return:
+ *	if can demangle then a a newly allocate string is returned.
+ *	if cannot demangle, then NULL is returned
+ *
+ * Note that caller is responsible for freeing demangled string
+ */
+char *
+java_demangle_sym(const char *str)
+{
+	char *buf, *ptr;
+	char *p;
+	size_t len, l1;
+
+	if (!str)
+		return NULL;
+
+	/* find start of retunr type */
+	p = strrchr(str, ')');
+	if (!p)
+		return NULL;
+
+	/*
+	 * expansion factor estimated to 3x
+	 */
+	len = strlen(str) * 3 + 1;
+	buf = malloc(len);
+	if (!buf)
+		return NULL;
+
+	buf[0] = '\0';
+	/*
+	 * get return type first
+	 */
+	ptr = __demangle_java_sym(p+1, NULL, buf, len, MODE_TYPE);
+	if (!ptr)
+		goto error;
+
+	/* add space between return type and function prototype */
+	l1 = strlen(buf);
+	buf[l1++] = ' ';
+
+	/* process function up to return type */
+	ptr = __demangle_java_sym(str, p + 1, buf + l1, len - l1, MODE_PREFIX);
+	if (!ptr)
+		goto error;
+
+	return buf;
+error:
+	free(buf);
+	return NULL;
+}
+
+
 static int dso__load_perf_map(struct dso *dso, struct map *map,
 			      symbol_filter_t filter)
 {
@@ -1257,6 +1447,7 @@ static int dso__load_perf_map(struct dso *dso, struct map *map,
 		u64 start, size;
 		struct symbol *sym;
 		int line_len, len;
+		char *name;
 
 		line_len = getline(&line, &n, file);
 		if (line_len < 0)
@@ -1279,7 +1470,9 @@ static int dso__load_perf_map(struct dso *dso, struct map *map,
 		if (len + 2 >= line_len)
 			continue;
 
-		sym = symbol__new(start, size, STB_GLOBAL, line + len);
+		name = line + len;
+
+		sym = symbol__new(start, size, STB_GLOBAL, name);
 
 		if (sym == NULL)
 			goto out_delete_line;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 1650dcb..2a6e23e 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -295,4 +295,5 @@ int compare_proc_modules(const char *from, const char *to);
 int setup_list(struct strlist **list, const char *list_str,
 	       const char *list_name);
 
+char * java_demangle_sym(const char *str);
 #endif /* __PERF_SYMBOL */
-- 
1.9.1